GLPI MCP Server — 45 AI Tools | Claude, ChatGPT & More

GLPI MCP ServerGLPI MCP server with 45 ready-to-use AI tools. Connect GLPI to Claude, ChatGPT, Gemini, or any MCP-compatible AI assistant. Cloud MCP connector — no install, no Docker, works from any browser.Category: Developer Tools. 45 tools available. Authentication: API Key.Manage your IT helpdesk and assets through conversationWhy GLPI + AI?GLPI is powerful but navigating its interface for quick ticket lookups, asset searches, and status checks is slow. Stop clicking through menus to find a ticket or check a computer — just ask your AI.Example prompts you can send your AI about GLPI

Ask: "Show all open high-priority tickets"
AI does: AI searches tickets with status=open and priority=high, returning a sorted list with assignees and categories.

Ask: "Create an incident: "VPN not connecting for remote users" with high urgency"
AI does: AI creates the ticket with the specified title, urgency level, and type=Incident, returning the new ticket ID.

Ask: "How many computers are running Windows 10?"
AI does: AI searches the computer inventory filtering by OS name containing "Windows 10", returning the count and list.

Ask: "Check license compliance for Microsoft Office"
AI does: AI retrieves the software entry and its licenses, showing used vs available seats and expiration dates.

Featured GLPI Tools

search-tickets: Search GLPI tickets with powerful filters. This is the PRIMARY tool for finding specific tickets. Returns ticket ID, name, status, type, urgency, priority, category, requester, dates, and assignment info. WHEN TO USE: User asks "find open tickets", "show high-urgency incidents", "tickets about printer", "what tickets were created this week?", "show pending tickets assigned to me", or ANY filtered ticket search. ALWAYS prefer this over list-tickets when the user mentions any filter criteria. STATUS VALUES: "new" (1), "processing" (2, assigned), "planned" (3), "pending" (4, waiting), "solved" (5), "closed" (6). Use "open" as shorthand to match new + processing + planned + pending (all non-resolved). URGENCY/PRIORITY VALUES: "very low" (1), "low" (2), "medium" (3), "high" (4), "very high" (5). TYPE VALUES: "incident" (1) or "request" (2). EXAMPLES: "Show open high-urgency tickets" → status="open", urgency="high". "Find tickets about printer from last week" → text="printer", date_from="2026-02-27", date_to="2026-03-06". "Show all pending incidents" → status="pending", type="incident". "Tickets assigned to user John" → requester="John". STEP-BY-STEP for helpdesk triage: 1) search-tickets with status="new" to find unassigned tickets, 2) get-ticket for full details on each, 3) assign-ticket to route to the right technician.

get-ticket: Get full details of a specific GLPI ticket by its ID. Returns name (title), content (description body as HTML), status, type, urgency, priority, impact, category, requester, assigned user/group, entity, dates (open/solve/close), followups (comments), tasks, and solution if present. This returns MORE detail than search-tickets — use this when you need the full description, comments, tasks, or solution text. WHEN TO USE: User asks "show me ticket 42", "what's the description of that ticket?", "who is working on this?", "what comments are on this ticket?", "has this ticket been solved?", or when you need full details after finding a ticket via search-tickets. EXAMPLE: id=42 → returns full ticket details including HTML content body, all followups, tasks, and solution. STEP-BY-STEP for ticket investigation: 1) search-tickets to find the ticket ID, 2) get-ticket for full details, 3) optionally add-ticket-followup to post an update or add-ticket-solution to resolve it.

create-ticket: Create a new GLPI ticket. Returns the new ticket ID and a link to view it. Requires: name (title) and content (description). Optional: type, urgency, priority, category_id, requester_id. WHEN TO USE: User asks "create a ticket", "log an incident", "submit a request", "open a helpdesk ticket", "report a problem", or any request to create a new ITSM ticket. CRITICAL: "name" is the ticket TITLE (short summary). "content" is the DESCRIPTION BODY (detailed explanation). Content is provided as plain text and automatically converted to HTML by GLPI. TYPE: "incident" (something is broken, default) or "request" (user needs something). URGENCY VALUES: 1 or "very low", 2 or "low", 3 or "medium" (default), 4 or "high", 5 or "very high". PRIORITY VALUES: Same scale as urgency. If omitted, GLPI auto-calculates from urgency + impact. EXAMPLES: "Create an incident for printer not working" → name="Printer on 3rd floor not printing", content="The HP LaserJet on the 3rd floor east wing has been offline since this morning. Error light is blinking red.", type="incident", urgency="high". "Submit a request for new laptop" → name="New laptop request", content="Need a new laptop for new hire starting March 15. Specs: 16GB RAM, 512GB SSD.", type="request". STEP-BY-STEP when category is unknown: 1) list-ticket-categories to find the right category_id, 2) create-ticket with that category_id. STEP-BY-STEP to create and assign: 1) search-users to find the technician's user_id, 2) create-ticket, 3) assign-ticket with the user_id.

list-computers: List GLPI computers (desktops, laptops, servers) with pagination. Returns computer ID, name, serial number, OS name, location, status, manufacturer, model, and last update date. WHEN TO USE: User asks "show all computers", "list servers", "what machines do we have?", or when you need a quick paginated view of the computer inventory. NOTE: For filtered searches (by name, serial, OS), use search-computers instead. EXAMPLE: page=1, per_page=10 → returns the first 10 computers. STEP-BY-STEP for asset audit: 1) list-computers to browse inventory, 2) get-computer for full details including installed software.

get-ticket-stats: Get aggregated ticket statistics. Returns counts grouped by status, urgency, priority, type, and category. Provides a high-level dashboard view of helpdesk workload without listing individual tickets. WHEN TO USE: User asks "how many open tickets?", "show ticket stats", "helpdesk overview", "ticket dashboard", "what's the workload?", "how many incidents vs requests?", or any aggregate/summary question about tickets. NOTE: Optionally filter by status to get stats for a subset (e.g., only open tickets by category). EXAMPLES: "Overall helpdesk stats" → no parameters. Returns { byStatus: { new: 12, processing: 34, pending: 8, ... }, byUrgency: { ... }, ... }. "Stats for open tickets only" → status="open". STEP-BY-STEP for daily standup report: 1) get-ticket-stats for the big picture, 2) search-tickets with status="new" to see unassigned tickets, 3) search-tickets with urgency="high" for escalation candidates.

list-software-licenses: List GLPI software licenses. Returns license ID, name, software name, serial/product key, license type, number (quantity purchased), and usage count (quantity in use). Optionally filter by software_id to see licenses for a specific software. WHEN TO USE: User asks "show software licenses", "check license compliance", "how many licenses do we have?", "are we over-licensed on Office?", "license audit", or any license management question. CRITICAL: Compare "number" (purchased quantity) vs usage count to detect over- or under-licensing. EXAMPLES: "All licenses" → no parameters. "Licenses for software 12" → software_id=12. STEP-BY-STEP for compliance audit: 1) search-software to find the software ID, 2) list-software-licenses with software_id to see purchased vs in-use counts, 3) flag any software where usage exceeds purchased licenses.

Frequently Asked Questions about GLPIHow do I connect GLPI to Claude or ChatGPT?Create a free LearnToSpeak.ai account, add your GLPI credentials in the dashboard, and paste the generated OAuth URL into Claude.ai's custom connectors or ChatGPT's developer apps. The integration runs fully in the cloud — no desktop app, no CLI, no local install.Does it cost anything to connect GLPI?The GLPI integration is free during the LearnToSpeak.ai public beta. You only need a paid plan from Anthropic or OpenAI (Claude Pro/Max/Team or ChatGPT Plus/Pro/Team) since custom connectors require it on the AI provider side.Which AI assistants support the GLPI connector?Claude.ai (Pro, Max, Team, Enterprise) and ChatGPT (Plus, Pro, Team) both support the GLPI integration via the MCP (Model Context Protocol) standard. The same credentials work across both platforms — add the connector once, use it everywhere.How many GLPI tools does my AI get access to?Your AI gets 45 ready-to-use tools for GLPI, covering the most common read and write operations. Each tool is a discrete action the AI can call on demand — no multi-step prompting, no screen scraping, no workarounds.Is it safe to give an AI access to my GLPI account?Yes. Your GLPI credentials are encrypted at rest with AES-256-GCM and only decrypted in memory when the AI makes a request. LearnToSpeak.ai uses OAuth 2.1 with mandatory PKCE for the AI-to-platform connection, and you can revoke access instantly from the dashboard. We never store or log the actual tool responses returned to the AI.Why use LearnToSpeak.ai instead of running an MCP server locally?Cloud MCP servers work from any browser on any device — no Node.js install, no Docker, no local ports, no maintenance. Configure GLPI once in the dashboard and your AI connects from claude.ai or chat.openai.com directly. That's the entire value proposition: web AI assistants don't read your filesystem, they read our servers.What is the GLPI MCP server?The GLPI MCP server is a cloud-hosted integration that gives AI assistants direct access to GLPI through 45 tools via the Model Context Protocol (MCP) standard. It works with Claude, ChatGPT, Gemini, and any MCP-compatible AI — no local installation or Docker required.How do I connect GLPI to Claude via MCP?Sign up at LearnToSpeak.ai, add your GLPI credentials, and copy the generated MCP URL into Claude.ai's custom connectors (Settings → Developer → Custom Connectors). The cloud MCP server handles the connection — no CLI, no local server, no Docker.How do I connect GLPI to ChatGPT via MCP?Sign up at LearnToSpeak.ai, add your GLPI credentials, and copy the generated MCP URL into ChatGPT's developer apps (Settings → Apps → Advanced → Developer mode). Works with any ChatGPT Plus, Pro, or Team account.What can AI do with GLPI through MCP?GLPI offers 45 MCP tools covering Manage IT assets, tickets, and helpdesk operations in GLPI. Ask your AI to perform any of these actions in natural language — it calls the right tool automatically.What is MCP (Model Context Protocol)?MCP is an open standard that lets AI assistants like Claude, ChatGPT, and Gemini connect directly to external apps and services. LearnToSpeak.ai hosts cloud MCP servers so you don't need to install anything locally — your AI connects from any browser.Related MCP Servers

GitHub MCP Server — 44 tools

GitLab MCP Server — 90 tools

NetBox MCP Server — 179 tools

Cisco CPNR MCP Server — 36 tools

Grafana MCP Server — 50 tools

Browse all 34 MCP servers